© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179658
    Prev
    Next
    INDEX
    Explanations

    declared war

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining code logic and projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    codone
    0.51
     ရှ
    0.47
     原子
    0.47
    ග්
    0.47
     Insgesamt
    0.47
     ຮ
    0.46
     biomed
    0.46
     塩
    0.46
     է
    0.46
    ाइंड
    0.46
    POSITIVE LOGITS
    به
    0.51
     কাব
    0.45
     pretext
    0.45
     imaginary
    0.44
    FAQ
    0.43
    Kab
    0.43
    essing
    0.42
    IVERY
    0.42
    Theoretical
    0.41
     constructor
    0.41
    Activations Density 0.000%

    No Known Activations